INDEX

Explanations

terms related to risk assessment and risk factors

oai_token-act-pair · gpt-4o-mini Triggered by @bot

near "risk"

np_acts-logits-general · gemini-2.0-flash

risk of disease or assessment

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

parsedMessage

-0.66

signable

-0.66

 Wikimedijinoj

-0.65

hoven

-0.65

contentLoaded

-0.65

İstinadlar

-0.61

Buildable

-0.56

 témoin

-0.56

Idle

-0.56

 Geller

-0.56

POSITIVE LOGITS

 risks

0.83

 Risks

0.82

RISK

0.81

Risks

0.78

 risk

0.78

Risk

0.77

 Risk

0.76

 RISK

0.73

risk

0.71

RIS

0.65

Activations Density 0.137%

terms related to risk assessment and risk factors

near "risk"

risk of disease or assessment

No Comments

No Known Activations